© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43406
    Prev
    Next
    INDEX
    Explanations

    random

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    -3.03
     enam
    -2.81
     bliss
    -2.69
     pretende
    -2.59
     Können
    -2.52
    }$.
    -2.47
    但我
    -2.41
    都会
    -2.33
     haha
    -2.33
     legge
    -2.31
    POSITIVE LOGITS
    鋮
    4.25
    蘩
    3.50
    禵
    3.47
    ⭏
    3.20
    鸶
    3.19
    鷓
    3.16
    翾
    3.02
    脔
    2.98
    蒹
    2.91
    玧
    2.77
    Activations Density 0.017%

    No Known Activations